医学
肺癌
肿瘤科
接收机工作特性
内科学
间变性淋巴瘤激酶
阶段(地层学)
生存分析
无进展生存期
淋巴瘤
放射科
总体生存率
生物
古生物学
恶性胸腔积液
作者
Donghui Hou,Xiaomin Zheng,Wei Song,Xiaoqing Liu,Sicong Wang,Lina Zhou,Xian Tao,Lv Lv,Qi Sun,Yujing Jin,Zewei Zhang,Lieming Ding,Ning Wu,Suping Zhao
标识
DOI:10.1177/02841851221119621
摘要
The prognosis of lung cancer varies widely, even in cases wherein the tumor stage, genetic mutation, and treatment regimens are the same. Thus, an effective means for risk stratification of patients with lung cancer is needed.To develop and validate a combined model for predicting progression-free survival and risk stratification in patients with advanced anaplastic lymphoma kinase (ALK)-positive non-small cell lung cancer (NSCLC) treated with ensartinib.We analyzed 203 tumor lesions in 114 patients and evaluated average radiomic feature measures from all lesions at baseline and changes in these features after early treatment (Δradiomic features). Combined models were developed by integrating clinical with radiomic features. The prediction performance and clinical value of the proposed models were evaluated using receiver operating characteristic analysis, calibration curve, decision curve analysis (DCA), and Kaplan-Meier survival analysis.Both the baseline and delta combined models achieved predictive efficacy with a high area under the curve. The calibration curve and DCA indicated the high accuracy and clinical usefulness of the combined models for tumor progression prediction. In the Kaplan-Meier analysis, the delta and baseline combined models, Δradiomic signature, and two selected clinical features could distinguish patients with a higher progression risk within 42 weeks. The delta combined model had the best performance.The combination of clinical and radiomic features provided a prognostic value for survival and progression in patients with NSCLC receiving ensartinib. Radiomic-signature changes after early treatment could be more valuable than those at baseline alone.
科研通智能强力驱动
Strongly Powered by AbleSci AI